Reltio Data Science

Get insight-ready data to bring your AI and ML ideas to life.

You can use Reltio Data Science to apply complex data and graph analytics against reliable data in Reltio Connected Cloud. This can be done through Reltio's solution accelerators or external third-party tools.

Reltio Data Science is designed for both business users and data management experts such as data analysts and data scientists. Business users work with profiles in Reltio Connected Cloud. Data scientists leverage Spark engine and tools like Qubole or Databricks to design and run analytics algorithms on top of the business data, and provide users with relevant insights, recommendations, forecasts, and more.

Key Features

Reltio Data Science comes with the following features:

  • Bi-directional connector between the Reltio platform and Apache Spark to assist in aggregation, calculation, enrichment, segmentation, machine learning, and graph analytics
  • Automated initial and ongoing ingestion of entities, relationships, interactions, and RDM data from the Reltio platform through S3 into Apache Spark
  • API to write-back the derived insights to the Reltio platform as analytical attributes
  • Reltio APIs that leverage Spark libraries for optimal processing
  • Auto-scaling platform independent of your Reltio tenant
  • UI built for business users, technical users, and data scientists

Third-Party Products

Reltio Data Science uses the following third-party products for analytics and jobs management:

  • Apache Spark 2.3 is the currently supported analytics engine.
  • Qubole Data Service (QDS) is the recommended platform for running Spark jobs.


Reltio Data Science is distributed as a separate Reltio product. Customers interested in Reltio Data Science should contact Reltio Support to get the necessary entitlement.